Upload config.json with huggingface_hub
Browse files- config.json +32 -0
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attention_o_bias": false,
|
3 |
+
"attention_qk_norm": true,
|
4 |
+
"attention_qkv_bias": false,
|
5 |
+
"codebook_size": 4096,
|
6 |
+
"dim": 1024,
|
7 |
+
"dropout": 0.0,
|
8 |
+
"fast_attention_o_bias": false,
|
9 |
+
"fast_attention_qk_norm": false,
|
10 |
+
"fast_attention_qkv_bias": false,
|
11 |
+
"fast_dim": 1024,
|
12 |
+
"fast_head_dim": 64,
|
13 |
+
"fast_intermediate_size": 3072,
|
14 |
+
"fast_n_head": 16,
|
15 |
+
"fast_n_local_heads": 8,
|
16 |
+
"head_dim": 128,
|
17 |
+
"initializer_range": 0.03125,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"max_seq_len": 8192,
|
20 |
+
"model_type": "dual_ar",
|
21 |
+
"n_fast_layer": 4,
|
22 |
+
"n_head": 16,
|
23 |
+
"n_layer": 28,
|
24 |
+
"n_local_heads": 8,
|
25 |
+
"norm_eps": 1e-06,
|
26 |
+
"num_codebooks": 10,
|
27 |
+
"rope_base": 1000000,
|
28 |
+
"scale_codebook_embeddings": true,
|
29 |
+
"tie_word_embeddings": false,
|
30 |
+
"use_gradient_checkpointing": true,
|
31 |
+
"vocab_size": 155776
|
32 |
+
}
|